Innovative Projects Realized

Explore thousands of successful projects resulting from collaboration between organizations and post-secondary talent.

29670 Completed Projects

2811
AB
4990
BC
801
MB
663
NL
825
SK
8841
ON
9197
QC
95
PE
568
NB
1088
NS

Projects by Category

Towards a Deep Multimodal Similarity Learning for Text and Image Embeddings Fusion

Turquoise Technology Solutions Inc. (“Turquoise”) is a Google Partner firm based in Montreal. They have been working on recommender systems for books and recipes. They are currently interested in improving the accuracy of their recommender systems. In order to improve such a system, the goal is to extract the model of customers’ preferences using both visual and textual interactions via processing the images of a product and texts left as comments respectively. This proposal concentrates on developing an image feature extraction using a deep convolutional autoencoder architecture with an intention to interface with a textual data. Using the image embedding vectors outputted by the network, a search method based on the K-nearest neighbor algorithm is proposed to calculate the similarity between an input image. Upon the performance of the model in measuring the image similarity, the search method can find the similarity through a fusion space obtained from the concatenated textual and image embeddings.

View Full Project Description
Faculty Supervisor:

Javad Dargahi

Student:

Partner:

Turquoise Technology Solutions Inc

Discipline:

Engineering

Sector:

Artificial Intelligence; Technology; Commercial Services

University:

Concordia University

Program:

Accelerate

Développement d’une stratégie de structuration de production et commercialisation à grande échelle d’une solution médicale de cellule cyberphysique autonome

Baüne désire concrétiser un premier cellule cyberphysique autonome permettant de proposer pour les soins médicaux à distance. Ce produit est un module connecté de surveillance médicale et se présente comme un espace adaptable grandeur nature avec des panneaux motorisés permettant l‘intégration de multiples capteurs de santé des patients.

View Full Project Description
Faculty Supervisor:

Fabiano Armellini

Student:

Partner:

Baüne

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

Polytechnique Montréal

Program:

Business Strategy Internship

Modèle de réserves stochastiques incorporant le jugement actuariell

L’utilisation de modèles statistiques pour décrire l’évolution du passif des polices est très recherché par l’industrie de l’assurance dommage, alors qu’il pose des problèmes théoriques extrêmement pertinents pour la science actuarielle. La dépendance entre les lignes d’affaires est un concept connu mais très complexe à quantifier. Une meilleure compréhension de cette dépendance par l’entreprise est cruciale. De plus, le fait de pouvoir incorporer le jugement actuariel aux modèles statistiques représente une extension naturelle aux méthodes classiques couramment utilisées dans l’industrie. Le modèle de réserves stochastiques incorporant le jugement actuariel adresse les défis mentionnés.

View Full Project Description
Faculty Supervisor:

Helene Cossette

Student:

Partner:

Co-operators (General Insurance)

Discipline:

Mathematics

Sector:

Finance and Insurance

University:

Université Laval

Program:

Accelerate

The plasma metabolomics footprint of dairy products: a reflection of consumption and a window to their cardiometabolic effects.

The general objective of this project is to identify unbiased and objective plasma metabolomics signatures of milk and cheese consumption. We will leverage data and stored, unthawed, plasma samples from 4 high quality randomized, crossover, feeding trials (RCTs) and 1 cohort of 200 free-living adults (eMECA) that were conducted or implemented at INAF research center over the past 15 years. The 4 RCTs investigated the impact of reduced fat milk (1% milk-fat) and/or regular-fat cheddar cheese (31% milk-fat) consumption on cardiometabolic health in a total of 185 adults with abdominal obesity. Therefore, the proposed project builds on a biobank that is second to none worldwide and that was created through nearly $3 million CAD of DFC investments in RCTs and human nutrition research over the past 15 years. The study will outcome on a unique demonstration of the ‘impact’ of milk and cheese consumption on cardiometabolic health, at the system level, providing novel insights on their health effects. By extension, the study will also outcome on a novel perspective on the impact of dairy fat consumption on cardiometabolic health as we will be able to compare the impact of reduced-fat milk with regular-fat cheese.

View Full Project Description
Faculty Supervisor:

Jean-Philippe Drouin-Chartier

Student:

Partner:

Dairy Farmers of Canada

Discipline:

Life Sciences

Sector:

Health and Related Sciences & Technology; Pharmaceuticals; Agriculture and Food

University:

Université Laval

Program:

Accelerate

Fairness Attacks on Large Language Models

Under the European General Data Protection Regulation (GDPR), businesses using customer data to make decisions must provide explanations in human terms on demand to the customer to explain their decision. The rise of natural language generation (NLG) and chain-of-thoughts (CoT) represents an opportunity to combine the power of deep learning, automated decision-making, and explainable AI. However, there are two important challenges standing in the way of making these systems useful. The first one is to align the AI system with human preferences in terms of decisions and explanations. The second one is to make the AI systems fair and robust to adversarial attacks. The aim of this project is to investigate the robustness of large language models (LLMs) to changes that should not affect their decisions, like meaningless textual reformulations, and changes to sensible information such as sex and race.

View Full Project Description
Faculty Supervisor:

Quentin Cappart;Louis-Martin Rousseau

Student:

Partner:

ServiceNow Canada

Discipline:

Computer science

Sector:

Transportation (excluding aerospace); Technology; Information and Communications Technology

University:

Polytechnique Montréal

Program:

Accelerate

HIVE Geospatial product/platform development

HIVE Geospatial’s mission is to enrich decision-making and facilitate more inclusive and equitable terrestrial and marine management through our proactive planning and collaboration software platform and services. Additional details are available at hivegeospatial.app. The Mitacs-supported internships will contribute to the continued evolution and improvement of the HIVE Geospatial platform, and allow us to address new requirements for existing customers and address new market segments in parallel with our business development efforts.

View Full Project Description
Faculty Supervisor:

Edward Brown

Student:

Partner:

HIVE Geospatial Inc.

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Memorial University of Newfoundland

Program:

Business Strategy Internship

Multi-sensor data streams from PLC to cloud computing platform

Instrumar Limited’s core technology platform is based on the measurement of electrical properties of materials that come in contact with its sensor. The sensor generates a tightly confined electromagnetic field that detects the properties as material enters this field. The sensor is sensitive to the amount, the shape, its density, temperature, conductivity, impurities, moisture content and flow speed of the material. The sensors sample data in real time and provide feedback based on parameters that are determined through extensive testing. This sensor is being used in multiple industries such as aerospace and industrial manufacturing. Two of our more successful applications are in the ice detection and polymer fiber manufacturing. Instrumar receives terabytes of data from its installations worldwide. It is one of our goals to turn this unprocessed high volume data into value added information
Using the latest analytical tools has identified many areas where we can use additional data from a variety of sensors to improve our ability to provide valuable information into quality and other problems that occur at customer facilities.
Instrumar is also now competing with other companies who can pull in data from other sensors and be able to provide intelligent information to the customer.
Building this new platform will allow us to compete and grow beyond being a sensor only company who can partner with these manufacturing companies in a more fulfilling manner. It can give us a competitive edge in the market.

View Full Project Description
Faculty Supervisor:

Vinicius Prado da Fonseca

Student:

Partner:

Instrumar

Discipline:

Engineering

Sector:

Manufacturing

University:

Memorial University of Newfoundland

Program:

Business Strategy Internship

Using Translation Models to Decode Overt Speech from BCI

Creating speech neuroprostheses, or devices that can help restore the ability to speak to people who have lost it due to neurological damage or disorder is extremely important because it can greatly improve the quality of life for these individuals. Despite this, there has not been a widely successful solution to this issue yet because creating a device that can effectively interface with the brain and restore speech is a technically challenging task that requires advances in neuroscience and engineering. Therefore there is very little publicly available data of people producing speech with implanted brain-computer interfaces. As a concequence, researchers struggle with creating generalizible and accurate algorithms for decoding speech. This works aims to re-use the models of natural language translation to inform the decoding model about language semantics. This can substantially decrease the amount of needed data for accurate predictions. Moreover, we aim to use transfer learning techniques to transfer knowledge between algorithms trained on different participants to address the issue of generalization.

View Full Project Description
Faculty Supervisor:

Bo Wang

Student:

Partner:

National University of Kyiv-Mohyla Academy

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology; Biotechnology; Artificial Intelligence

University:

University of Toronto

Program:

Globalink Research Award

AccuTrack – Encodeur linéaire pour l’OptoWire

Afin de débloquer les artères coronaires, des tuteurs métalliques sont implantés à l’aide de fil-guides. L’OptoWire, de la compagnie québécoise OpSens Inc, est un fil-guide muni d’un capteur de pression à fibre optique qui permet de déterminer l’ampleur du bloquage dans les artères, et si un tuteur est nécessaire. Afin d’améliorer le diagnostic, un concept d’encodeur linéaire est proposé afin de détecter avec le déplacement de l’OptoWire dans le patient. Cela permettrait, en plus de savoir si un tuteur est nécessaire ou non, de déterminer avec précision la longueur du tuteur à implanter. Avec cet instrument innovateur, les cardiologues pourraient optimiser le traitement des patients et ainsi minimiser les risques de complications.

View Full Project Description
Faculty Supervisor:

Daniel Côté

Student:

Partner:

OpSens Inc.

Discipline:

Engineering

Sector:

Manufacturing

University:

Université Laval

Program:

Accelerate

Scaling Up Trauma- and Violence-Informed Physical Activity for Mental Health and Well-being

Despite the overwhelming evidence that physical activity promotes overall positive health, there are limited trauma-and-violence-informed health promotion strategies directed towards equity-owed populations. Women experiencing multiple marginalization’s face numerous barriers to participation in physical activity and are at higher risk for negative health outcomes. Engaging in regular physical activity can have numerous benefits such as improving mental health, decreasing depression, anxiety, and other health conditions which may be important to improving outcomes for those who have experienced trauma and violence. Women who experience(d) trauma and violence may be a population who can physically, socially, emotionally, and mentally benefit from engaging in trauma-and violence-informed physical activity (TVIPA) interventions. This research proposes to increase participation in physical activity for women living in marginalizing situations who tend to be underrepresented, and systematically excluded, in physical activity. In collaboration with St. Mary’s Home, strategies to increase access to/improve awareness of the potential physical and mental health benefits of TVIPA will be explored. In addition, TVIPA will be leveraged to create support networks among mental health and other essential service providers to enhance the delivery of their services through the development of a social learning space.

View Full Project Description
Faculty Supervisor:

Francine Darroch

Student:

Partner:

Mental Health Research Canada;St. Mary’s Home

Discipline:

Sociology

Sector:

Other services (except public administration); Professional, scientific and technical services

University:

Carleton University

Program:

Accelerate

Modélisation et évaluation des vibrations induites par les réducteurs à lit fluidisé

Lorsque des équipements industriels sont en marche, cela produit beaucoup de vibration. Si ces vibrations ne sont pas contrôlées ou si la structure du bâtiment est mal conçue, cela risque de nuire à la sécurité des occupants. Dans le cas de certains équipements comme les réducteurs à lit fluidisé, les vibrations que cet équipement produit sont très aléatoires, il est ainsi très difficile de bien prédire la réponse de ce dernier. Cela peut conduire à un comportement inacceptable de la structure du support d’équipement ou à un surdimensionnement important. Afin d’avoir une conception la plus optimale possible, une comparaison de la réponse réelle des équipements à celle obtenue d’un modèle par éléments finis devra être faite.

View Full Project Description
Faculty Supervisor:

Rola Assi

Student:

Partner:

Hatch Ltd (Montreal, QC)

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

École de technologie supérieure

Program:

Accelerate

Sterilization of Foie Gras – Demonstration ofSafety and Stability under Minimal ProcessingConditions

The goal of this project is to demonstrate the adequacy of mild thermal processes (Fo ~1 min) for meeting the requirements for commercial sterility of foie gras in cans or jars. It was previously demonstrated that the sensitivity of thermal destruction of microbial spores increases with an increase in FFA concentration. The proposed project will be focused on the safety and stability of the product under industrial processing conditions. The study would encompass the following: incorporate a characterized surrogate (C. supergenes) at a high concentration level into foie gras in the can or the jar, establish an equivalent thermal process and demonstrate deliverance of the desired degree of sterility. In this study selected spore formers will be incorporated into fois gras, contained in small pouches/pans/simulated particles and placed in the central regions of test cans, and are given processes equivalent to different Fo values. The survivors will determine the level of severity of the process and incubation tests will determine the stability of the product, storage studies will indicate stability.

View Full Project Description
Faculty Supervisor:

Hosahalli Ramaswamy

Student:

Partner:

Aurpal Inc

Discipline:

Physics

Sector:

Wholesale trade

University:

McGill University

Program:

Accelerate

Previous
1…1,0061,0071,0081,0091,0101,0111,012…2,473
Next

Join a thriving innovation ecosystem.

Subscribe to our newsletter now!

Subscribe